All of the memory models in question are based on data-race-free, which says (in essence) that as long as all cross-thread interactions follow happens-before, then you can act as if everybody is sequentially-consistent.
The original Java 5 memory model only offered sequentially-consistent atomics to establish cross-thread happens-before in a primitive way. The C++11 memory model added three more kinds of atomics: acquire/release, consume/release (which was essentially a mistake [1]), and relaxed atomics (which, to oversimplify, establish atomicity without happens-before). Pretty much every memory model since C++11--which includes the Rust memory model--has based its definition on that memory model, with most systems defaulting an otherwise unadorned atomic operation to sequentially-consistent. Even Java has retrofitted ways to get weaker atomic semantics [2].
As a practical matter, most atomics could probably safely default to acquire/release over fully sequentially-consistent. The main difference between the two is that sequentially-consistent is safer if you've got multiple atomic variables in play (e.g., you're going with some fancy lockless algorithm), whereas acquire/release tends to largely be safe if there's only one atomic variable of concern (e.g., you're implementing locks of some kind).
[1] A consume operation is an acquire, but only for loads data-dependent on the load operation. This is supposed to represent a situation that requires no fences on any system not named Alpha, but it turns out for reasons™ that compilers cannot reliably preserve source-level data dependencies, so no compiler really implemented consume/release.
[2] Even Java 5 may have had it in sun.misc.Unsafe; I was never familiar with that API, so I don't know for certain.
> as long as all cross-thread interactions follow happens-before, then you can act as if everybody is sequentially-consistent.
I don't think that's the actual guarantee. You can enforce happens-before with just acquire/release, but AFIK that's not enough to recover SC in the general case[1].
As far as I understand, The Data Race Free - Sequentially Consistent memory model (DRF-SC) used by C++11 (and I think Java), says that as long as all operation on atomics are SC and the program is data-race-free, then the whole program can be proven to be sequentially consistent.
[1] but it might in some special cases, for example when all operations are mutex lock and unlock.
The original Java 5 memory model only offered sequentially-consistent atomics to establish cross-thread happens-before in a primitive way. The C++11 memory model added three more kinds of atomics: acquire/release, consume/release (which was essentially a mistake [1]), and relaxed atomics (which, to oversimplify, establish atomicity without happens-before). Pretty much every memory model since C++11--which includes the Rust memory model--has based its definition on that memory model, with most systems defaulting an otherwise unadorned atomic operation to sequentially-consistent. Even Java has retrofitted ways to get weaker atomic semantics [2].
As a practical matter, most atomics could probably safely default to acquire/release over fully sequentially-consistent. The main difference between the two is that sequentially-consistent is safer if you've got multiple atomic variables in play (e.g., you're going with some fancy lockless algorithm), whereas acquire/release tends to largely be safe if there's only one atomic variable of concern (e.g., you're implementing locks of some kind).
[1] A consume operation is an acquire, but only for loads data-dependent on the load operation. This is supposed to represent a situation that requires no fences on any system not named Alpha, but it turns out for reasons™ that compilers cannot reliably preserve source-level data dependencies, so no compiler really implemented consume/release.
[2] Even Java 5 may have had it in sun.misc.Unsafe; I was never familiar with that API, so I don't know for certain.